{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4Y6FBZIX6TL65JZZXOERHRRZ2E","short_pith_number":"pith:4Y6FBZIX","canonical_record":{"source":{"id":"2505.22664","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-28T17:59:59Z","cross_cats_sorted":[],"title_canon_sha256":"e3e517af92326c6cc89b2ea75bf886e7f84a0845ca6567d60c234c8c2a08f334","abstract_canon_sha256":"59c5f445f53427d735c694faf40ce9eb8b0adff5cd226085e0879949f3104597"},"schema_version":"1.0"},"canonical_sha256":"e63c50e517f4d7eea739bb8913c639d125aa95693e7e20a159633bd6b62f216b","source":{"kind":"arxiv","id":"2505.22664","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22664","created_at":"2026-07-05T11:47:23Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22664v2","created_at":"2026-07-05T11:47:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22664","created_at":"2026-07-05T11:47:23Z"},{"alias_kind":"pith_short_12","alias_value":"4Y6FBZIX6TL6","created_at":"2026-07-05T11:47:23Z"},{"alias_kind":"pith_short_16","alias_value":"4Y6FBZIX6TL65JZZ","created_at":"2026-07-05T11:47:23Z"},{"alias_kind":"pith_short_8","alias_value":"4Y6FBZIX","created_at":"2026-07-05T11:47:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4Y6FBZIX6TL65JZZXOERHRRZ2E","target":"record","payload":{"canonical_record":{"source":{"id":"2505.22664","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-28T17:59:59Z","cross_cats_sorted":[],"title_canon_sha256":"e3e517af92326c6cc89b2ea75bf886e7f84a0845ca6567d60c234c8c2a08f334","abstract_canon_sha256":"59c5f445f53427d735c694faf40ce9eb8b0adff5cd226085e0879949f3104597"},"schema_version":"1.0"},"canonical_sha256":"e63c50e517f4d7eea739bb8913c639d125aa95693e7e20a159633bd6b62f216b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:23.681641Z","signature_b64":"fwxS8xsYtv9kBhirfArgoKBvtulST6IzI4n0n4vWMJRi5o5HKYgz8xFMtwz9vOWz3a1QnXw6CTs+rxelQD7IDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e63c50e517f4d7eea739bb8913c639d125aa95693e7e20a159633bd6b62f216b","last_reissued_at":"2026-07-05T11:47:23.681136Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:23.681136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.22664","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:47:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2s86vC7BvpoJ0S4ZG92EaHp0TGRZhSwODabGNSLpublhzXBYCalh2rGlcb0XJF4tSDfGlp6pyo74ZXvSL6IiAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:23:23.022918Z"},"content_sha256":"30a9d4129143b65f43803ba94a631b9b3adfcc010f61e744ad4af2f65ecf00d8","schema_version":"1.0","event_id":"sha256:30a9d4129143b65f43803ba94a631b9b3adfcc010f61e744ad4af2f65ecf00d8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4Y6FBZIX6TL65JZZXOERHRRZ2E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Zero-Shot Vision Encoder Grafting via LLM Surrogates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Bhatele, Furong Huang, John Kirchenbauer, Kaiyu Yue, Menglin Jia, Rifaa Qadri, Tom Goldstein, Vasu Singla, Zikui Cai","submitted_at":"2025-05-28T17:59:59Z","abstract_excerpt":"Vision language models (VLMs) typically pair a modestly sized vision encoder with a large language model (LLM), e.g., Llama-70B, making the decoder the primary computational burden during training. To reduce costs, a potential promising strategy is to first train the vision encoder using a small language model before transferring it to the large one. We construct small \"surrogate models\" that share the same embedding space and representation language as the large target LLM by directly inheriting its shallow layers. Vision encoders trained on the surrogate can then be directly transferred to t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22664","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.22664/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:47:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kJCpcELH0YGGtNGyTH9ZnP7QacyJKA6XzV9cnp7HmAW41U8Vmn/p6DmKn0LguCFMhXgEOCjQ0+RrQAoyyU4aBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:23:23.023426Z"},"content_sha256":"04933e4e9482b495b48466fae6168f5cea71e636246df6e417f4c804def19f1b","schema_version":"1.0","event_id":"sha256:04933e4e9482b495b48466fae6168f5cea71e636246df6e417f4c804def19f1b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4Y6FBZIX6TL65JZZXOERHRRZ2E/bundle.json","state_url":"https://pith.science/pith/4Y6FBZIX6TL65JZZXOERHRRZ2E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4Y6FBZIX6TL65JZZXOERHRRZ2E/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T00:23:23Z","links":{"resolver":"https://pith.science/pith/4Y6FBZIX6TL65JZZXOERHRRZ2E","bundle":"https://pith.science/pith/4Y6FBZIX6TL65JZZXOERHRRZ2E/bundle.json","state":"https://pith.science/pith/4Y6FBZIX6TL65JZZXOERHRRZ2E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4Y6FBZIX6TL65JZZXOERHRRZ2E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4Y6FBZIX6TL65JZZXOERHRRZ2E","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"59c5f445f53427d735c694faf40ce9eb8b0adff5cd226085e0879949f3104597","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-28T17:59:59Z","title_canon_sha256":"e3e517af92326c6cc89b2ea75bf886e7f84a0845ca6567d60c234c8c2a08f334"},"schema_version":"1.0","source":{"id":"2505.22664","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22664","created_at":"2026-07-05T11:47:23Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22664v2","created_at":"2026-07-05T11:47:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22664","created_at":"2026-07-05T11:47:23Z"},{"alias_kind":"pith_short_12","alias_value":"4Y6FBZIX6TL6","created_at":"2026-07-05T11:47:23Z"},{"alias_kind":"pith_short_16","alias_value":"4Y6FBZIX6TL65JZZ","created_at":"2026-07-05T11:47:23Z"},{"alias_kind":"pith_short_8","alias_value":"4Y6FBZIX","created_at":"2026-07-05T11:47:23Z"}],"graph_snapshots":[{"event_id":"sha256:04933e4e9482b495b48466fae6168f5cea71e636246df6e417f4c804def19f1b","target":"graph","created_at":"2026-07-05T11:47:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.22664/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision language models (VLMs) typically pair a modestly sized vision encoder with a large language model (LLM), e.g., Llama-70B, making the decoder the primary computational burden during training. To reduce costs, a potential promising strategy is to first train the vision encoder using a small language model before transferring it to the large one. We construct small \"surrogate models\" that share the same embedding space and representation language as the large target LLM by directly inheriting its shallow layers. Vision encoders trained on the surrogate can then be directly transferred to t","authors_text":"Abhinav Bhatele, Furong Huang, John Kirchenbauer, Kaiyu Yue, Menglin Jia, Rifaa Qadri, Tom Goldstein, Vasu Singla, Zikui Cai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-28T17:59:59Z","title":"Zero-Shot Vision Encoder Grafting via LLM Surrogates"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22664","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:30a9d4129143b65f43803ba94a631b9b3adfcc010f61e744ad4af2f65ecf00d8","target":"record","created_at":"2026-07-05T11:47:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"59c5f445f53427d735c694faf40ce9eb8b0adff5cd226085e0879949f3104597","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-28T17:59:59Z","title_canon_sha256":"e3e517af92326c6cc89b2ea75bf886e7f84a0845ca6567d60c234c8c2a08f334"},"schema_version":"1.0","source":{"id":"2505.22664","kind":"arxiv","version":2}},"canonical_sha256":"e63c50e517f4d7eea739bb8913c639d125aa95693e7e20a159633bd6b62f216b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e63c50e517f4d7eea739bb8913c639d125aa95693e7e20a159633bd6b62f216b","first_computed_at":"2026-07-05T11:47:23.681136Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:47:23.681136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fwxS8xsYtv9kBhirfArgoKBvtulST6IzI4n0n4vWMJRi5o5HKYgz8xFMtwz9vOWz3a1QnXw6CTs+rxelQD7IDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:47:23.681641Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.22664","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30a9d4129143b65f43803ba94a631b9b3adfcc010f61e744ad4af2f65ecf00d8","sha256:04933e4e9482b495b48466fae6168f5cea71e636246df6e417f4c804def19f1b"],"state_sha256":"ebe720f71195af34e1016ac0f6c98e72bde93999009ada5a0572941a251acb0d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lUtqUPApv/uSRngmnF7DZLwAjkuuJKwEomL4gwFb2e1Z1Mg6pJ6zZS5Fw/T1YQ4enkcc3PlJ6Lc4FbTf3C97DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T00:23:23.028180Z","bundle_sha256":"6fc8941a8380653aeb6bb059713869f83bcaa2403cba12f87234aaad0f0ece27"}}